https://rijournals.

com/biological-and-applied-science/
RESEARCH INVENTION JOURNAL OF BIOLOGICAL AND APPLIED SCIENCES 3(3):30-33, 2024

©RIJBAS Publications Online ISSN: 1115-6171

Print ISSN: 1597-2879

Integrating AI and IoT for Smart Manufacturing

Kato Jumba K.

Faculty of Science and Technology Kampala International University Uganda

ABSTRACT
Smart Manufacturing (SM) is leading the Fourth Industrial Revolution (Industry 4.0) in manufacturing.
SM optimises production via Smart Products, Operations, and Factories. This article defines, explains,
and applies AI and IoT to SM. AI's data-driven decision-making and IoT's real-time data interchange
improve industrial systems' intelligence and efficiency. We study how smart factories may harmonise
various technologies for real-time adaptation, predictive maintenance, quality control, and operational
excellence. The report also analyses AI-IoT integration problems and suggests future research and
implementation techniques.
Keywords: Industry 4.0, Smart Manufacturing (SM), Artificial Intelligence (AI), Internet of Things
(IoT), Smart Factories (SFs).

INTRODUCTION
The advent of the Fourth Industrial Revolution, known as Industry 4.0, has engendered a significant
transformation in manufacturing practices. A key facet of Industry 4.0 is the advent of Smart
Manufacturing (SM), which synergistically integrates Smart Products (SPs) and Smart Operations (SOs)
in Smart Factories (SFs). In recent years, IoT technologies, particularly sensors, have gained traction in
manufacturing as a pipeline for data analytics related to SPs. In parallel, Artificial Intelligence (AI)
algorithms have emerged as a tool for data-driven decision support in manufacturing. Despite the
encapsulation of these technologies in a greater context of SM, a cohesive integration of their definitions
and roles in SM is lacking. The goal of this paper is to elucidate the definitions of IoT and AI
technologies, demonstrate how these technologies can be integrated into SM, and discuss the implications
of such integration [1]. The Internet of Things (IoT) is characterized as "a dynamic global network
infrastructure with self-configuring capabilities based on standard and interoperable communication
protocols where physical and virtual 'things' have identities, physical attributes, and virtual personalities,
and use intelligent interfaces to interact with other entities." IoT enables the interconnection of various
devices and smart objects, thus enabling remote monitoring and control capabilities. Smart Products
(SPs) are products that leverage IoT technologies to interact with stakeholders, such as suppliers and
customers. IoT-enabled SPs can provide data regarding their condition, performance, and environment to
other stakeholders, which can be used for data-driven decision support [2]. Artificial Intelligence (AI)
encompasses systems or machines that emulate "intelligent" human-like behaviors. AI algorithms enable
systems to analyze data to make inferences and generate knowledgeable output. In recent years, AI
algorithms have gained traction in manufacturing contexts, particularly for data-driven decision support
through the processing of data from SPs. The dataset is expected to be fragmented and heterogeneous
due to the decentralization of SPs. A particular challenge for the implementation of AI algorithms in this
context is data preprocessing, with several steps needed before data is ready for analysis. Data
preprocessing encompasses data cleansing, integration, transformation, and reduction [3].
FOUNDATIONS OF AI AND IOT
Artificial Intelligence (AI) and Internet of Things (IoT): Definitions, Characteristics, and Core
30

Technologies
Artificial Intelligence (AI) refers to a computer system's capability to perform cognitive tasks that
Page

characteristically require human intelligence, such as perceiving, reasoning, learning, and planning.
https://rijournals.com/biological-and-applied-science/
Industry representations of AI often project a future world dominated by socio-technical systems for the
automatic generation of networks of computers and robots, all of which will be outfitted with "intelligent"
decision-making software. However, here, AI is defined more modestly, as a computer system that can
evaluate the surrounding world using sensors and make decisions depending on the evidence. AI
technologies include machine learning, natural language processing, speech recognition, neural networks,
and so on [4]. According to IoT World Forum, the Internet of Things (IoT) is the connection of
everyday objects to the internet, facilitating easy monitoring and controlling. IoT applications in an
industrial context are called Industrial IoT (IIoT). As with AI, IIoT is often presented overly positively
in industry technical literature and market analysis and predictions. State-of-the-art IIoT technologies
and solutions include smart sensors, smart object representational ontologies, service-oriented software
architecture, and cloud-based service mathematics [5].
Generational characteristics of AI and IoT Technologies for Smart Manufacturing
As highlighted in Figure 1, AI and IoT technologies should arguably be understood as constituent
components of a smarter generational development, rather than solely as underlying core technologies.
More precisely, they represent a conceptual transition from the second, fixed, and localized generation
(SFM2.0) to the third, networked and dynamically flexible, generation (SFM3.0) of factories. In SFM2.0,
the capabilities of sensors, robots, and machines are internally represented by shared ontologies and
models. They are fixed prior to a batch of production or a production line's design phase. Computer
simulations of the digital model are used for design optimization and re-design for changes in external
conditions, such as varying production volumes or new product types [6]. SFM3.0 moves towards
dynamic representations for decision-making, using learning-based approaches. Smart objects in factories
3.0 generate continuous, real-time data streams. AI uses this data to develop local knowledge for situation
awareness. Objects should share this knowledge with peers for a broader understanding. The shared data
allows factories with SFM3.0 to make informed production decisions. (313 characters) [7].
APPLICATIONS OF AI IN SMART MANUFACTURING
The application of artificial intelligence (AI) in industrial Internet of Things (IIoT-based smart
manufacturing is an active area of research, helping organizations to utilize data and enhance value-added
services. The advance in communication technology has made it possible to equip manufacturing
machines with sensors and collect data. This collected data can be utilized for predictive maintenance,
quality prediction, process selection, collision avoidance, repair action recommendation, etc., using
different AI techniques (machine learning, deep learning, reinforcement learning) [8]. The
manufacturing sector is adopting IIoT-driven smart manufacturing to advance industrial automation and
competition. The use of smart sensors, smart machines, and wireless communication devices facilitates the
data exchange between machines, workstations, and management information systems. Artificial
intelligence (AI), a part of the development in Industry 4.0, allows the automation of the manufacturing
environment. The historical process data of the industrial setup can be utilized for manufacturing
applications using different AI techniques and models. The literature has been reviewed to present the
various applications of AI in IIoT-based smart manufacturing. Applications like predictive maintenance,
fault identification, quality prediction, process selection, and others have been categorized, and the work
of the researchers has been summarized [9]. The smart factory comprises several smart machines with
sensors and computer systems. These smart machines collect the manufacturing process data to detect
faults in real-time, generate alarms, and store them in the database or cloud. Predictive maintenance
(PdM) aims to upgrade the condition-based monitoring of the machine and reduce unintended failures.
The remaining useful life (RUL) of the machine can be estimated using machine learning and other
techniques from the condition monitoring information. Various researchers have worked on this
application, and their efforts have been detailed. Time-series analysis of industrial data for various
manufacturing processes has also been presented. Fault detection, alarm generation, and collision
avoidance initiative have also been reported in recent works [10].
APPLICATIONS OF IOT IN SMART MANUFACTURING
The Internet of Things (IoT) is extensively utilized in smart manufacturing processes, with numerous
applications contributing to improved productivity, streamlined operations, and safer environments. This
discussion focuses on several noteworthy applications of IoT in smart factories [11]. IoT is employed in
smart factories to enable machine-to-machine communication, allowing for precise, real-time data. This
technology provides manufacturers with valuable insights, ushering in a new era of intelligent
31

manufacturing driven by impactful testing, analysis, prediction, and recommendation technologies.

Sensors in manufacturing facilities gather data from machines, while centralized data platforms track the
Page

data and analyze it to form recommendations. By automating or reforming operations based on these
recommendations, factories benefit from low operational costs, high equipment reliability, and reduced
https://rijournals.com/biological-and-applied-science/
production disruptions [12]. Conditions can be monitored and controlled remotely, assisting operators in
making maximum production quantity decisions. Smart dust, a development of tiny, wireless sensors,
accumulates information on temperature, pressure, and humidity for condition recognition. The data is
analyzed, local maintenance activities are scheduled if necessary, and corrective or preventive measures
are suggested [13]. The Industrial Internet of Things is composed of interconnected physical devices
that compile and analyze massive amounts of data. The technology can detect production volume, defects,
and labor efficiency, as well as notify operators and engineers of potential problems. Intelligence
assessment models adopted by industries improve productivity and quality, focusing on evaluating
aspects of decision-making, business intelligence, and equipment monitoring [14]. Warehouse
management is improved through smarter systems featuring RFID tracking capabilities for palletized
products, producing real-time views of stock levels and modern systems solving congestion issues. IoT-
powered smart meters improve energy efficiency and reduce operational costs by gathering data on
consumption patterns. Smart supply chains predict delays, allowing manufacturers to take corrective
actions and minimize losses [15].
INTEGRATION OF AI AND IOT IN SMART MANUFACTURING
Over the past decade, AI and IoT have gained popularity in various applications. IoT uses sensors, smart
devices, cloud storage, and the internet to exchange real-time data. AI enables intelligent behavior
through real-time data analysis using algorithms like machine learning. AI and IoT have been integrated
in domains such as agriculture, healthcare, transportation, stock market, and smart cities. Smart
manufacturing (Industry 4.0) offers an opportunity to transform the industry with AI and IoT. It
combines manufacturing processes with communication and information technologies to create efficient
and high-quality smart factories. AI and IoT in smart manufacturing enable real-time adaptability and
optimization. Smart devices are interconnected through IoT platforms for information exchange. AI
optimizes processes and includes fault detection and feedback control. Unsupervised learning is used for
data analytics [16].
CONCLUSION
The integration of AI and IoT in Smart Manufacturing marks a significant milestone in the evolution of
the manufacturing industry. AI enhances the processing and analysis of large datasets generated by IoT
devices, enabling real-time decision-making and optimization in production processes. The fusion of these
technologies results in more adaptive, efficient, and intelligent manufacturing systems that can predict
maintenance needs, improve product quality, and reduce downtime. However, challenges such as data
preprocessing, system interoperability, and the need for robust security measures must be addressed to
fully realize the potential of AI and IoT in smart manufacturing. Future research should focus on
overcoming these barriers and exploring new applications of AI and IoT to further enhance
manufacturing capabilities.
REFERENCES
1. Phuyal S, Bista D, Bista R. Challenges, opportunities and future directions of smart
manufacturing: a state of art review. Sustainable Futures. 2020. sciencedirect.com
2. Mouha RARA. Internet of things (IoT). Journal of Data Analysis and Information Processing.
2021. scirp.org
3. Peres RS, Jia X, Lee J, Sun K, Colombo AW, Barata J. Industrial artificial intelligence in industry
4.0-systematic review, challenges and outlook. IEEE access. 2020 Dec 7; 8:220121-39. ieee.org
4. Trappey A, Trappey CV, Hsieh A. An intelligent patent recommender adopting machine
learning approach for natural language processing: A case study for smart machinery technology
mining. Technological Forecasting and Social Change. 2021 Mar 1; 164:120511. [HTML]
5. Laghari AA, Wu K, Laghari RA, Ali M, Khan AA. A review and state of art of Internet of Things
(IoT). Archives of Computational Methods in Engineering. 2021 Jul 14:1-9. researchgate.net
6. Saha M, Panda SK, Panigrahi S. A modified Brown and Gibson model for cloud service selection.
International Journal of Computational Science and Engineering. 2023;26(4):430-44. [HTML]
7. Sahal R, Breslin JG, Ali MI. Big data and stream processing platforms for Industry 4.0
requirements mapping for a predictive maintenance use case. Journal of manufacturing systems.
2020. researchgate.net
8. Behrendt A, De Boer E, Kasah T, Koerber B, Mohr N, Richter G. Leveraging Industrial IoT and
advanced technologies for digital transformation. McKinsey & Company. 2021 Feb:1-75.
32

sightmachine.com
9. Ullo SL, Sinha GR. Advances in smart environment monitoring systems using IoT and sensors.
Page

Sensors. 2020. mdpi.com

https://rijournals.com/biological-and-applied-science/
10. Wang B, Lei Y, Li N, Wang W. Multiscale convolutional attention network for predicting
remaining useful life of machinery. IEEE Transactions on Industrial Electronics. 2020 Jun
25;68(8):7496-504. [HTML]
11. Sahoo S, Lo CY. Smart manufacturing powered by recent technological advancements: A review.
Journal of Manufacturing Systems. 2022. [HTML]
12. Chandra Shekhar Rao V, Kumarswamy P, Phridviraj MS, Venkatramulu S, Subba Rao V. 5G
enabled industrial internet of things (IIoT) architecture for smart manufacturing. InData
Engineering and Communication Technology: Proceedings of ICDECT 2020 2021 (pp. 193-
201). Springer Singapore. researchgate.net
13. Dobrilovic D, Brtka V, Stojanov Z, Jotanovic G, Perakovic D, Jausevac G. A model for working
environment monitoring in smart manufacturing. Applied sciences. 2021 Mar 23;11(6):2850.
mdpi.com
14. Huo R, Zeng S, Wang Z, Shang J, Chen W, Huang T, Wang S, Yu FR, Liu Y. A comprehensive
survey on blockchain in industrial internet of things: Motivations, research progresses, and
future challenges. IEEE Communications Surveys & Tutorials. 2022 Jan 10;24(1):88-122.
[HTML]
15. Abir SMAA, Anwar A, Choi J, Kayes ASM. Iot-enabled smart energy grid: Applications and
challenges. IEEE access. 2021. ieee.org
16. Khang A, Rath KC, Satapathy SK, Kumar A, Das SR, Panda MR. Enabling the future of
manufacturing: integration of robotics and IoT to smart factory infrastructure in industry 4.0.
InHandbook of Research on AI-Based Technologies and Applications in the Era of the
Metaverse 2023 (pp. 25-50). IGI Global. [HTML]

CITE AS: Kato Jumba K. (2024). Integrating AI and IoT for Smart Manufacturing.
RESEARCH INVENTION JOURNAL OF BIOLOGICAL AND APPLIED SCIENCES
3(3):30-33.

33
Page